facebookresearch / facebookresearch/segment-anything
Is there only one input shape for vit to correctly output mask？
Open
- Dominant language
- Jupyter Notebook
- Stars
- 54.9k
- Forks
- 6.4k
- PR merge metrics
- No merged PRs in 30d
Description
If the input of VIt is not 1024x1024 but something else, such as 1024x512 or 768x512, can sam also accurately output the mask
Contributor guide
Assessment
This issue has not been assessed yet.